Drop Oceania

Before dropping Oceania, let’s check the number of rows in gapminder, and the levels of continent.

gapminder %>% 
  # get the number of rows and levels of continent
  summarize(
    nrow = nrow(gapminder),
    nlevels = nlevels(gapminder$continent)
  ) %>% 
  # show the table
  knitr::kable(col.names = c("Number of rows", "Levels of `continent`"))

Let’s first try to drop Oceania, and show the number of rows, and the levels of continent.

# drop Oceania
drop <- gapminder %>% 
  filter(continent != "Oceania")

drop %>% 
  # get the number of rows and levels of continent
  summarize(
    nrow = nrow(drop),
    nlevels = nlevels(drop$continent)
  ) %>% 
  # show the table
  knitr::kable(col.names = c("Number of rows after dropping", "Levels of `continent` after dropping"))

Here we can see, even we remove all rows associated with the continent of Oceania (so the number of rows decrease), the levels of continent is unchanged. However, it is a wrong value. To fix it, we need to droplevels() to solve the issue.

# drop levels
drop_levels <- drop %>% 
  droplevels()

drop_levels %>% 
  # get the number of rows and levels of continent
  summarize(
    nrow = nrow(drop_levels),
    nlevels = nlevels(drop_levels$continent)
  ) %>% 
  # show the table
  knitr::kable(col.names = c("Number of rows after dropping levels", "Levels of `continent` after dropping levels"))

To summarize, we address the number of rows and the levels of continent before and after removing Oceania.

# build a tibble with statistics
summary <- cbind(
  before = c(
    nrow(gapminder),
    nlevels(gapminder$continent)
  ),
  after = c(
    nrow(drop_levels),
    nlevels(drop_levels$continent)
  )
)

# assign row names
rownames(summary) <- c("Number of rows", "Levels")

# display the table
summary %>% 
  knitr::kable()

Reorder the levels of country and continent

Let’s show a preview of our dropped version of gapminder before reordering.

# show previews
head(drop_levels) %>% 
  knitr::kable()

tail(drop_levels) %>% 
  knitr::kable()

From a bigger picture, this data frame is ordered by the alphabetical order of country. Let’s try to reorder the levels of country by the maximum population over the years using fct_reorder(). Note that it is reordered in ascending order, so the first level is the one with least maximum population over the year.

fct_reorder(
  # reorder country
  drop_levels$country,
  # by pop
  drop_levels$pop,
  # using maximum
  max) %>%
  # show preview of resultant levels
  levels() %>% 
  head() %>% 
  knitr::kable(col.names = c("`country` after reordering"))

In order to check our results, we manually calculate the maximum population and order it.

drop_levels %>% 
  # group by country
  group_by(country) %>% 
  # calcuate maximum population for each country
  summarize(
    max_pop = max(pop)
  ) %>% 
  # arrange by max_pop
  arrange(max_pop) %>%
  # show preview
  head() %>% 
  knitr::kable(col.names = c("country", "Maximum population over the years"))

So our operation using fct_reorder is correct.

We can do the same thing on continent. For example, we reorder its levels by the average life expectancy.

fct_reorder(
  # reorder continent
  drop_levels$continent,
  # by lifeExp
  drop_levels$lifeExp,
  # using mean
  mean) %>%
  # show preview of resultant levels
  levels() %>% 
  head() %>% 
  knitr::kable(col.names = c("`continent` after reordering"))

We also double-check the results.

drop_levels %>% 
  # group by continent
  group_by(continent) %>% 
  # calcuate mean lifeExp for each continent
  summarize(
    mean_lifeExp = mean(lifeExp)
  ) %>% 
  # arrange by mean_lifeExp
  arrange(mean_lifeExp) %>%
  # show preview
  head() %>% 
  knitr::kable(col.names = c("continent", "Average life expectancy over the years"))

Characterize the (derived) data

In the previous section, we try to create two examples using fct_reorder() and arrange(), with identical results. Now, we try to reuse the first example and see if these two functions affect figures generated.

Let’s try the first example, using fct_reorder() only.

drop_levels %>%
  # try to only show a continent
  filter(continent == "Americas") %>% 
  # group by country
  group_by(country) %>% 
  # calcuate maximum population for each country
  mutate(
    max_pop = max(pop)
  ) %>%
  # show preview of resultant levels
  ggplot(aes(x = max_pop, y = fct_reorder(country, pop, max), color = country)) +
  # make it a scatterplot
  geom_point() + 
  # scale x axis by log10
  scale_x_log10() +
  # change axis labels
  xlab("Maximum population") +
  ylab("country")

Let’s do it with arrange() only.

drop_levels %>% 
  # try to only show a continent
  filter(continent == "Americas") %>% 
  # group by country
  group_by(country) %>% 
  # calcuate maximum population for each country
  summarize(
    max_pop = max(pop)
  ) %>% 
  # arrange by max_pop
  arrange(max_pop) %>%
  # show preview of resultant levels
  ggplot(aes(x = max_pop, y = country, color = country)) +
  # make it a scatterplot
  geom_point() + 
  # scale x axis by log10
  scale_x_log10() +
  # change axis labels
  xlab("Maximum population") +
  ylab("country")

Now we use fct_reorder() with arrange().

drop_levels %>% 
  # try to only show a continent
  filter(continent == "Americas") %>% 
  # group by country
  group_by(country) %>% 
  # calcuate maximum population for each country
  mutate(
    max_pop = max(pop)
  ) %>% 
  # arrange by max_pop
  arrange(max_pop) %>%
  # show preview of resultant levels
  ggplot(aes(x = max_pop, y = fct_reorder(country, pop, max), color = country)) +
  # make it a scatterplot
  geom_point() + 
  # scale x axis by log10
  scale_x_log10() +
  # change axis labels
  xlab("Maximum population") +
  ylab("country")

Finding(s): using fct_reorder() (no matter with arrange() or not) will change the order of levels shown in figures, while using arrange() along will not affect the order of levels.

write_csv()/read_csv()

# write to csv
write_csv(data, "data_csv.csv")
# read from csv
data_csv <- read_csv("data_csv.csv")

## Parsed with column specification:
## cols(
##   country = col_character(),
##   max_pop = col_double()
## )

# show summary of the data
data_csv %>% 
  glimpse()

## Observations: 142
## Variables: 2
## $ country <chr> "Sao Tome and Principe", "Iceland", "Djibouti", "Equat...
## $ max_pop <dbl> 199579, 301931, 496374, 551201, 708573, 710960, 720230...

# show previews
head(data_csv) %>% 
  knitr::kable()

tail(data_csv) %>% 
  knitr::kable()

Finding(s): using CSV format, it requires R to parse each column with default formats. Therefore, the class of country changes from <fct> to <chr>. However, the data keeps unchanged.

saveRDS()/readRDS()

# save to rds
saveRDS(data, "data_rds.rds")
# read from rds
data_rds <- readRDS("data_rds.rds")

# show summary of the data
data_rds %>% 
  glimpse()

## Observations: 142
## Variables: 2
## $ country <fct> Sao Tome and Principe, Iceland, Djibouti, Equatorial G...
## $ max_pop <dbl> 199579, 301931, 496374, 551201, 708573, 710960, 720230...

# show previews
head(data_rds) %>% 
  knitr::kable()

tail(data_rds) %>% 
  knitr::kable()

Finding(s): saveRDS() and readRDS() can keep both data and classes of each column.

dput()/dget()

# put to file
dput(data, "data.txt")
# get from file
data_get <- dget("data.txt")

# show summary of the data
data_get %>% 
  glimpse()

## Observations: 142
## Variables: 2
## $ country <fct> Sao Tome and Principe, Iceland, Djibouti, Equatorial G...
## $ max_pop <dbl> 199579, 301931, 496374, 551201, 708573, 710960, 720230...

# show previews
head(data_get) %>% 
  knitr::kable()

tail(data_get) %>% 
  knitr::kable()

Finding(s): dput() and dget() can also keep both data and classes of each column.

Arguments of ggsave()

Let’s play around arguments of ggsave(). For example, width, height, resolution, and text scale.

Differenct widths and heights

# default width and height
ggsave("./ggsave/1.png")

## Saving 7 x 5 in image

1.png

# arbitrary width and height
ggsave("./ggsave/2.png", width = 10, height = 5)

2.png

Different resolutions

Here we try to generate image of two resolutions, one as normal and one very low.

# normal resolution
ggsave("./ggsave/3.png", dpi = 300)

## Saving 7 x 5 in image

3.png

# low resolution
ggsave("./ggsave/4.png", dpi = 10)

## Saving 7 x 5 in image

4.png

Various graphics devices

# vector format
ggsave("./ggsave/5.eps", device = "eps")

## Saving 7 x 5 in image

(An ESP file cannot be loaded into an HTML file, so it is ignored.)

# raster format
ggsave("./ggsave/6.bmp", device = "bmp")

## Saving 7 x 5 in image

6.bmp

The diffience is, we can still modify vector format images, while it is not possible to do it on raster format images.

Explicit provision of the plot object p

Without explicit provision of the plot object p, ggsave() always tries to save the lastest figure (in our case, it is p_new). Therefore, we need to provide the plot object if we want to save other figures, for example, p_ori.

# save p_ori
ggsave("./ggsave/7.png", plot = p_ori)

## Saving 7 x 5 in image

7.png

fct_relevel()

We can use fct_relevel() to manually reorder levels. For example, we can move Canada to be the first data in this example (which in the figure is the bottom one).

drop_levels %>% 
  # try to only show a continent
  filter(continent == "Americas") %>% 
  # group by country
  group_by(country) %>% 
  # calcuate maximum population for each country
  summarize(
    max_pop = max(pop)
  ) %>% 
  # arrange by max_pop
  arrange(max_pop) %>%
  # show preview of resultant levels
  ggplot(aes(x = max_pop, y = fct_relevel(country, "Canada"), color = country)) +
  # make it a scatterplot
  geom_point() + 
  # scale x axis by log10
  scale_x_log10() +
  # change axis labels
  xlab("Maximum population") +
  ylab("country") +
  # highlight Canada
  scale_y_discrete(labels = c("Canada" = expression(bold(Canada)), parse = TRUE))

fct_reorder2()

We can use fct_reorder2() to reorder by two variables. For example, in the following example, we reorder by population first then GDP per capita (though it is not obvious).

gapminder %>% 
  # show only Oceania
  filter(continent == "Oceania") %>% 
  # pop as x axis and gdpPercap as y axis
  ggplot(aes(x = pop, y = gdpPercap, color = fct_reorder2(country, pop, gdpPercap, min))) +
  # make it a line plot
  geom_line() + 
  # change label
  labs(color = "Country") +
  # scale x by log10
  scale_x_log10()

fct_infreq() and fct_rev()

We use fct_infreq() to order levels in increasing frequency and fct_rev() to reverse order. They are usually used in bar plots.

gapminder %>% 
  # show only a continent
  filter(continent == "Americas") %>% 
  # filter countreis with gdpPercap larger than 15,000
  filter(gdpPercap >= 15000) %>% 
  # reorder levels of country
  mutate(
    country = country %>% fct_infreq() %>% fct_rev()
  ) %>% 
  # country as x axis
  ggplot(aes(x = country, fill = country)) +
  # make it as a bar plot
  geom_bar()

fct_recode()

fct_recode() can be used to manully change the names of levels. For example, we try to change the name of “United States” in the above example.

gapminder %>% 
  # show only a continent
  filter(continent == "Americas") %>% 
  # filter countreis with gdpPercap larger than 15,000
  filter(gdpPercap >= 15000) %>% 
  # reorder levels of country, and change name of "United States"
  mutate(
    country = country %>% fct_infreq() %>% fct_rev() %>% 
      fct_recode(
        "USA" = "United States"
      )
  ) %>% 
  # country as x axis
  ggplot(aes(x = country, fill = country)) +
  # make it as a bar plot
  geom_bar()

fct_collapse()

We can try to use fct_collapse() to manually combine levels into groups. For example, we combined “Canada” and “USA” together in the above example.

gapminder %>% 
  # show only a continent
  filter(continent == "Americas") %>% 
  # filter countreis with gdpPercap larger than 15,000
  filter(gdpPercap >= 15000) %>% 
  # reorder levels of country, and change name of "United States", and combine "Canada" and "USA"
  mutate(
    country = country %>% fct_infreq() %>% fct_rev() %>% 
      fct_recode(
        "USA" = "United States"
      ) %>% 
      fct_collapse(
        "North Americas" = c("Canada", "USA")
      )
  ) %>% 
  # country as x axis
  ggplot(aes(x = country, fill = country)) +
  # make it as a bar plot
  geom_bar()

fct_lump()

fct_lump() try to automaticaly aggregate groups.

gapminder %>% 
  # show only a continent
  filter(continent == "Americas") %>% 
  # filter countreis with gdpPercap larger than 15,000
  filter(gdpPercap >= 15000) %>% 
  # reorder levels of country, and let forcats lump groups for us
  mutate(
    country = country %>% fct_infreq() %>% fct_rev() %>% fct_lump()
  ) %>% 
  # country as x axis
  ggplot(aes(x = country, fill = country)) +
  # make it as a bar plot
  geom_bar()